Getting it into your agent
One page per mod, every tool's command on it. A separate URL per tool would split the same page into five that compete with each other.
npx skills add lucasmaher-hash/touch-designer-mcp --skill mcpb-bundlegit clone --depth 1 https://github.com/lucasmaher-hash/touch-designer-mcpWrote this? Show the measurements
A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.
[](https://agentmods.dev/skills/lucasmaher-hash/touch-designer-mcp/mcpb-bundle)<a href="https://agentmods.dev/skills/lucasmaher-hash/touch-designer-mcp/mcpb-bundle"><img src="https://agentmods.dev/badge/skills/lucasmaher-hash/touch-designer-mcp/mcpb-bundle/github.svg" alt="Measured on agentmods" height="20"></a>Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.
<a href="https://agentmods.dev/skills/lucasmaher-hash/touch-designer-mcp/mcpb-bundle"><img src="https://agentmods.dev/badge/skills/lucasmaher-hash/touch-designer-mcp/mcpb-bundle.svg" alt="Reviewed on agentmods" width="80" height="20"></a>What it costs to keep this loaded
Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.
| Model | Per session | Once invoked |
|---|---|---|
| Fable 5.1 | $0.00102 | $0.01085 |
| Opus 5 | $0.00051 | $0.00543 |
| Sonnet 5 | $0.00020 | $0.00217 |
| Haiku 4.5 | $0.00010 | $0.00109 |
Grade A, and why
mcpb-bundle scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 9d ago.
A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.
Nothing flagged
None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.
This is a copy
100% identical to mcpb-bundle — 0 lines differ, which has more behind it and is treated as the original. This page carries a canonical link to it rather than competing with it.
How it starts
The opening of the file, as written. The whole thing — 70 lines — stays where its author put it; the contents beside it link to each section on GitHub.
tdmcp Desktop bundle: .dxt → .mcpb
Anthropic renamed Desktop Extensions from DXT (.dxt, packer
@anthropic-ai/dxt, manifest key dxt_version) to MCPB (.mcpb, packer
@anthropic-ai/mcpb, manifest key manifest_version). Legacy .dxt still
installs in Codex Desktop, but new directory submissions should ship .mcpb.
What this repo already has
scripts/build-mcpb.mjs is already MCPB-aware: it tries @anthropic-ai/mcpb
first, falls back to legacy @anthropic-ai/dxt, then to a system zip. The
bundle stages manifest.json at the archive root + dist/, recipes/, td/,
README.md, LICENSE, package.json, and a production-only node_modules. So
the migration is mostly renaming the output + the references, not a rewrite.
dxt/manifest.json currently declares "manifest_version": "0.3" — already the
modern MCPB key (not the legacy dxt_version), so the manifest is largely correct.
The migration, concretely
- Manifest — verify, don't guess. Before touching
manifest_version, check what the installed packer accepts:npx --yes @anthropic-ai/mcpb --help(look forpack/validate). If it ships avalidatecommand, run it againstdxt/manifest.jsonand let it tell you. Only changemanifest_versionif validation demands it. A wrong value breaks install — this is why we verify rather than assume a number. - Output filename →
tdmcp.mcpb. Inscripts/build-mcpb.mjs: changeoutFiletotdmcp.mcpband update the log lines (they say.dxt). Keep the packer-preference order and the zip fallback intact — both must still work. Optionally rename the script file tobuild-mcpb.mjs(update the npm script if you do). - npm scripts (
package.json): renamebuild:dxt→build:mcpbpointing at the script. Only keep abuild:dxtalias if something external depends on the old name (grep first); otherwise replace it cleanly — no compatibility cruft. Check theversionscript too (it stagesdxt/manifest.json). - Reference sweep — change user-facing
.dxt→.mcpbin:docs/guide/{install,troubleshooting,glossary}.md+ theirdocs/pt/mirrors,docs/DEPLOYMENT.md,docs/reference/cli.md,scripts/setup.mjs,README.md. Also grep.github/for any release workflow that builds or uploadstdmcp.dxt/ runsbuild:dxt. - Release-asset URLs. Links to
releases/latest/download/tdmcp.dxtpoint at a published asset. After this change the next release shipstdmcp.mcpb; update those links to.mcpband record that a new release must be cut so the asset exists (the current v0.3.0 asset is still.dxt). Note this for the human in migration notes.
What this file has done since we first saw it
Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.
- 9d ago First seen · 70 lines · 102 tokens per session scan A 1f075d5b9edb
mcpb-bundle is a skill published in the GitHub repository lucasmaher-hash/touch-designer-mcp (0 stars, last pushed 1mo ago), licensed MIT. It adds 102 tokens to every session and 1,085 once invoked, about $0.0005 per session on Opus 5. A static security scan graded it A with 0 findings. It is 100% identical to mcpb-bundle, differing in 0 lines, and is treated as a copy.
Other skills, from other repositories
systematic-debugging
Use when encountering any bug, test failure, or unexpected behavior, before proposing fixes.
local-ai-agents
Build local-first AI agents that run entirely on a developer workstation with Microsoft Foundry Local and Qwen function-calling models. Covers Small Language Models (SLMs), the OpenAI-compatible local endpoint, sandboxed local tools, local RAG with Chroma, local MCP servers, hybrid cloud/local routing, and the…
next-cache-components-adoption
Turn on Cache Components in a Next.js app and resolve the blocking routes it surfaces. Use when the user wants to enable, adopt, or migrate to Cache Components, flip the cacheComponents flag, work through a flood of blocking-prerender / instant validation errors, run the cache-components-instant-false codemod, or…
insight-error-page
Write or audit an insight-kind error page for the Next.js dev overlay. Use when creating a new errors/ .mdx page, auditing an existing one, or checking that a page matches the framework fix cards. Covers page structure, title alignment, FixCard cards with Copy prompt button, code snippets, terminology verification…
next-cache-components-optimizer
Drive a Next.js route to instant navigation by setting up an agentic loop, under Cache Components / PPR, on initial load (hard navigation) and client-side navigation (soft navigation). Encode the goal as a failing @next/playwright instant() e2e and work it to green, one verified route at a time; the shipped test then…
next-partial-prefetching-adoption
Turn on Partial Prefetching in a Next.js app and work through the insights it surfaces. Use when the user wants to enable or adopt Partial Prefetching, flip the partialPrefetching flag, opt routes in with export const prefetch = 'partial', audit Link prefetch={true} behavior, preserve existing prefetched UI with…